@article{lightningopd20mitigatingstylebiasincross, title = {Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models}, author = {Yecheng Wu and Song Han and Han Cai}, year = {2026}, eprint = {2607.28449}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.28449}, }